Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    date and location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Editable
    0.44
     canvases
    0.41
     बॉस
    0.38
     alcal
    0.38
     Giveaway
    0.38
     الرجل
    0.38
    ឪ
    0.37
     Chairman
    0.36
     haft
    0.36
     Ombudsman
    0.36
    POSITIVE LOGITS
    と同様
    0.42
    Twilight
    0.40
    frameN
    0.39
    LQ
    0.39
    𝑄
    0.39
    新型コロナ
    0.38
    মনের
    0.37
    height
    0.36
    ované
    0.36
    LP
    0.35
    Act Density 0.000%

    No Known Activations